© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6098
    Prev
    Next
    INDEX
    Explanations

    mentions of academic institutions and scientific research conducted at the University of California, specifically focusing on studies, discoveries, and collaborations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.16
    0.5%
    404
    +0.14
    0.5%
    241
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.16
    0.07
    146
    +0.14
    0.06
    404
    +0.14
    0.06
    Negative Logits
    cause
    -1.01
    odan
    -0.93
    ogle
    -0.88
    andem
    -0.87
    tons
    -0.87
    ician
    -0.86
    wana
    -0.86
    warm
    -0.85
    ppo
    -0.84
    zer
    -0.83
    POSITIVE LOGITS
     Extension
    1.14
     Robotics
    1.12
     Teaching
    1.03
     Hosp
    1.02
     Merrill
    1.00
     Libraries
    0.96
     Laboratories
    0.94
     Graduate
    0.91
     Cooperative
    0.91
    uates
    0.90
    Activations Density 1.063%

    No Known Activations